
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import plotly 
import plotly.express as px
import plotly.graph_objs as go
import plotly.offline as py
from plotly.offline import iplot
from sklearn.cluster import KMeans
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler
from sklearn import metrics


df=pd.read_csv("C:/Users/Rahul Gupta/Documents/Dataset/football_data.csv",index_col=0)
df.head()


df.shape

(18207, 88)


df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 18207 entries, 0 to 18206
Data columns (total 88 columns):
 #   Column                    Non-Null Count  Dtype  
---  ------                    --------------  -----  
 0   ID                        18207 non-null  int64  
 1   Name                      18207 non-null  object 
 2   Age                       18207 non-null  int64  
 3   Photo                     18207 non-null  object 
 4   Nationality               18207 non-null  object 
 5   Flag                      18207 non-null  object 
 6   Overall                   18207 non-null  int64  
 7   Potential                 18207 non-null  int64  
 8   Club                      17966 non-null  object 
 9   Club Logo                 18207 non-null  object 
 10  Value                     18207 non-null  object 
 11  Wage                      18207 non-null  object 
 12  Special                   18207 non-null  int64  
 13  Preferred Foot            18159 non-null  object 
 14  International Reputation  18159 non-null  float64
 15  Weak Foot                 18159 non-null  float64
 16  Skill Moves               18159 non-null  float64
 17  Work Rate                 18159 non-null  object 
 18  Body Type                 18159 non-null  object 
 19  Real Face                 18159 non-null  object 
 20  Position                  18147 non-null  object 
 21  Jersey Number             18147 non-null  float64
 22  Joined                    16654 non-null  object 
 23  Loaned From               1264 non-null   object 
 24  Contract Valid Until      17918 non-null  object 
 25  Height                    18159 non-null  object 
 26  Weight                    18159 non-null  object 
 27  LS                        16122 non-null  object 
 28  ST                        16122 non-null  object 
 29  RS                        16122 non-null  object 
 30  LW                        16122 non-null  object 
 31  LF                        16122 non-null  object 
 32  CF                        16122 non-null  object 
 33  RF                        16122 non-null  object 
 34  RW                        16122 non-null  object 
 35  LAM                       16122 non-null  object 
 36  CAM                       16122 non-null  object 
 37  RAM                       16122 non-null  object 
 38  LM                        16122 non-null  object 
 39  LCM                       16122 non-null  object 
 40  CM                        16122 non-null  object 
 41  RCM                       16122 non-null  object 
 42  RM                        16122 non-null  object 
 43  LWB                       16122 non-null  object 
 44  LDM                       16122 non-null  object 
 45  CDM                       16122 non-null  object 
 46  RDM                       16122 non-null  object 
 47  RWB                       16122 non-null  object 
 48  LB                        16122 non-null  object 
 49  LCB                       16122 non-null  object 
 50  CB                        16122 non-null  object 
 51  RCB                       16122 non-null  object 
 52  RB                        16122 non-null  object 
 53  Crossing                  18159 non-null  float64
 54  Finishing                 18159 non-null  float64
 55  HeadingAccuracy           18159 non-null  float64
 56  ShortPassing              18159 non-null  float64
 57  Volleys                   18159 non-null  float64
 58  Dribbling                 18159 non-null  float64
 59  Curve                     18159 non-null  float64
 60  FKAccuracy                18159 non-null  float64
 61  LongPassing               18159 non-null  float64
 62  BallControl               18159 non-null  float64
 63  Acceleration              18159 non-null  float64
 64  SprintSpeed               18159 non-null  float64
 65  Agility                   18159 non-null  float64
 66  Reactions                 18159 non-null  float64
 67  Balance                   18159 non-null  float64
 68  ShotPower                 18159 non-null  float64
 69  Jumping                   18159 non-null  float64
 70  Stamina                   18159 non-null  float64
 71  Strength                  18159 non-null  float64
 72  LongShots                 18159 non-null  float64
 73  Aggression                18159 non-null  float64
 74  Interceptions             18159 non-null  float64
 75  Positioning               18159 non-null  float64
 76  Vision                    18159 non-null  float64
 77  Penalties                 18159 non-null  float64
 78  Composure                 18159 non-null  float64
 79  Marking                   18159 non-null  float64
 80  StandingTackle            18159 non-null  float64
 81  SlidingTackle             18159 non-null  float64
 82  GKDiving                  18159 non-null  float64
 83  GKHandling                18159 non-null  float64
 84  GKKicking                 18159 non-null  float64
 85  GKPositioning             18159 non-null  float64
 86  GKReflexes                18159 non-null  float64
 87  Release Clause            16643 non-null  object 
dtypes: float64(38), int64(5), object(45)
memory usage: 12.4+ MB


pd.set_option('display.max_rows',500)  
df.isna().sum()

ID                              0
Name                            0
Age                             0
Photo                           0
Nationality                     0
Flag                            0
Overall                         0
Potential                       0
Club                          241
Club Logo                       0
Value                           0
Wage                            0
Special                         0
Preferred Foot                 48
International Reputation       48
Weak Foot                      48
Skill Moves                    48
Work Rate                      48
Body Type                      48
Real Face                      48
Position                       60
Jersey Number                  60
Joined                       1553
Loaned From                 16943
Contract Valid Until          289
Height                         48
Weight                         48
LS                           2085
ST                           2085
RS                           2085
LW                           2085
LF                           2085
CF                           2085
RF                           2085
RW                           2085
LAM                          2085
CAM                          2085
RAM                          2085
LM                           2085
LCM                          2085
CM                           2085
RCM                          2085
RM                           2085
LWB                          2085
LDM                          2085
CDM                          2085
RDM                          2085
RWB                          2085
LB                           2085
LCB                          2085
CB                           2085
RCB                          2085
RB                           2085
Crossing                       48
Finishing                      48
HeadingAccuracy                48
ShortPassing                   48
Volleys                        48
Dribbling                      48
Curve                          48
FKAccuracy                     48
LongPassing                    48
BallControl                    48
Acceleration                   48
SprintSpeed                    48
Agility                        48
Reactions                      48
Balance                        48
ShotPower                      48
Jumping                        48
Stamina                        48
Strength                       48
LongShots                      48
Aggression                     48
Interceptions                  48
Positioning                    48
Vision                         48
Penalties                      48
Composure                      48
Marking                        48
StandingTackle                 48
SlidingTackle                  48
GKDiving                       48
GKHandling                     48
GKKicking                      48
GKPositioning                  48
GKReflexes                     48
Release Clause               1564
dtype: int64


data=df.copy()


data=data.drop(columns=['ID','Photo','Flag','Club Logo','Loaned From','Real Face','Release Clause'],axis=1)
data.shape

(18207, 81)


data.dropna(axis=0, inplace = True)
data.shape

(14751, 81)


data.isna().sum()

Name                        0
Age                         0
Nationality                 0
Overall                     0
Potential                   0
Club                        0
Value                       0
Wage                        0
Special                     0
Preferred Foot              0
International Reputation    0
Weak Foot                   0
Skill Moves                 0
Work Rate                   0
Body Type                   0
Position                    0
Jersey Number               0
Joined                      0
Contract Valid Until        0
Height                      0
Weight                      0
LS                          0
ST                          0
RS                          0
LW                          0
LF                          0
CF                          0
RF                          0
RW                          0
LAM                         0
CAM                         0
RAM                         0
LM                          0
LCM                         0
CM                          0
RCM                         0
RM                          0
LWB                         0
LDM                         0
CDM                         0
RDM                         0
RWB                         0
LB                          0
LCB                         0
CB                          0
RCB                         0
RB                          0
Crossing                    0
Finishing                   0
HeadingAccuracy             0
ShortPassing                0
Volleys                     0
Dribbling                   0
Curve                       0
FKAccuracy                  0
LongPassing                 0
BallControl                 0
Acceleration                0
SprintSpeed                 0
Agility                     0
Reactions                   0
Balance                     0
ShotPower                   0
Jumping                     0
Stamina                     0
Strength                    0
LongShots                   0
Aggression                  0
Interceptions               0
Positioning                 0
Vision                      0
Penalties                   0
Composure                   0
Marking                     0
StandingTackle              0
SlidingTackle               0
GKDiving                    0
GKHandling                  0
GKKicking                   0
GKPositioning               0
GKReflexes                  0
dtype: int64


#Number of duplicate rows
data.duplicated().sum()

0


#Cleaning the value and wage columns
def manipulate_mk(Value):
    if isinstance(Value,str):
        rep = Value.replace('€', '')
        if 'M' in rep:
            rep = float(rep.replace('M', ''))*1000000
        elif 'K' in Value:
            rep = float(rep.replace('K', ''))*1000
        return float(rep)

data['Value']=data['Value'].apply(lambda x:manipulate_mk(x))
data['Wage']=data['Wage'].apply(lambda x:manipulate_mk(x))


#Cleaning and Preprocessing the 'Joined' Column
data['Joined']=pd.to_datetime(data['Joined'])
data['Joined']=pd.DatetimeIndex(data['Joined']).year
data['Joined']=data['Joined'].replace(np.nan,0)
data['Joined']=data['Joined'].astype(str)


#Cleaning and Preprocessing the 'Contract Valid Until' Column
data['Contract Valid Until']=pd.to_datetime(data['Contract Valid Until'])
data['Contract Valid Until']=pd.DatetimeIndex(data['Contract Valid Until']).year
data['Contract Valid Until']=data['Contract Valid Until'].replace(np.nan,0)
data['Contract Valid Until']=data['Contract Valid Until'].astype(str)


#Cleaning and Preprocessing the 'Height' Column
def clean_height(val):
    obs=[]
    value=[]
    if isinstance(val,str):
        obs=val.split("'")
        a=obs[0]
        b=obs[1]
        value=(int(a)*12+int(b))/12
    return(value)
data['Height']=data['Height'].apply(clean_height)


#Cleaning and Preprocessing the 'Weight' Column
def clean_weight(val):
    obs=[]
    if isinstance(val,str):
        obs=int(val.replace('lbs',''))
    return(obs)

data['Weight']=data['Weight'].apply(lambda x:clean_weight(x))
data['Weight']=data['Weight'].astype(float)


#Cleaning columns like 'LS','ST','RS',etc.
def remove_plus(val):
    value=[]
    if isinstance(val,str):
        obs=val.split('+') 
        a=obs[0]
        b=obs[1]
        value=int(a)+int(b)
    return(value)

col=['LS', 'ST', 'RS','LW', 'LF', 'CF', 'RF', 'RW', 'LAM', 'CAM', 'RAM', 'LM', 'LCM', 'CM','RCM', 'RM', 'LWB', 'LDM', 'CDM', 'RDM', 'RWB', 'LB', 'LCB', 'CB','RCB', 'RB']
for i in col:
    data[i]=data[i].apply(remove_plus)
    data[i]=data[i].astype(float)


pd.set_option('display.max_columns',500) 
data.head()


data.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 14751 entries, 0 to 18206
Data columns (total 81 columns):
 #   Column                    Non-Null Count  Dtype  
---  ------                    --------------  -----  
 0   Name                      14751 non-null  object 
 1   Age                       14751 non-null  int64  
 2   Nationality               14751 non-null  object 
 3   Overall                   14751 non-null  int64  
 4   Potential                 14751 non-null  int64  
 5   Club                      14751 non-null  object 
 6   Value                     14751 non-null  float64
 7   Wage                      14751 non-null  float64
 8   Special                   14751 non-null  int64  
 9   Preferred Foot            14751 non-null  object 
 10  International Reputation  14751 non-null  float64
 11  Weak Foot                 14751 non-null  float64
 12  Skill Moves               14751 non-null  float64
 13  Work Rate                 14751 non-null  object 
 14  Body Type                 14751 non-null  object 
 15  Position                  14751 non-null  object 
 16  Jersey Number             14751 non-null  float64
 17  Joined                    14751 non-null  object 
 18  Contract Valid Until      14751 non-null  object 
 19  Height                    14751 non-null  float64
 20  Weight                    14751 non-null  float64
 21  LS                        14751 non-null  float64
 22  ST                        14751 non-null  float64
 23  RS                        14751 non-null  float64
 24  LW                        14751 non-null  float64
 25  LF                        14751 non-null  float64
 26  CF                        14751 non-null  float64
 27  RF                        14751 non-null  float64
 28  RW                        14751 non-null  float64
 29  LAM                       14751 non-null  float64
 30  CAM                       14751 non-null  float64
 31  RAM                       14751 non-null  float64
 32  LM                        14751 non-null  float64
 33  LCM                       14751 non-null  float64
 34  CM                        14751 non-null  float64
 35  RCM                       14751 non-null  float64
 36  RM                        14751 non-null  float64
 37  LWB                       14751 non-null  float64
 38  LDM                       14751 non-null  float64
 39  CDM                       14751 non-null  float64
 40  RDM                       14751 non-null  float64
 41  RWB                       14751 non-null  float64
 42  LB                        14751 non-null  float64
 43  LCB                       14751 non-null  float64
 44  CB                        14751 non-null  float64
 45  RCB                       14751 non-null  float64
 46  RB                        14751 non-null  float64
 47  Crossing                  14751 non-null  float64
 48  Finishing                 14751 non-null  float64
 49  HeadingAccuracy           14751 non-null  float64
 50  ShortPassing              14751 non-null  float64
 51  Volleys                   14751 non-null  float64
 52  Dribbling                 14751 non-null  float64
 53  Curve                     14751 non-null  float64
 54  FKAccuracy                14751 non-null  float64
 55  LongPassing               14751 non-null  float64
 56  BallControl               14751 non-null  float64
 57  Acceleration              14751 non-null  float64
 58  SprintSpeed               14751 non-null  float64
 59  Agility                   14751 non-null  float64
 60  Reactions                 14751 non-null  float64
 61  Balance                   14751 non-null  float64
 62  ShotPower                 14751 non-null  float64
 63  Jumping                   14751 non-null  float64
 64  Stamina                   14751 non-null  float64
 65  Strength                  14751 non-null  float64
 66  LongShots                 14751 non-null  float64
 67  Aggression                14751 non-null  float64
 68  Interceptions             14751 non-null  float64
 69  Positioning               14751 non-null  float64
 70  Vision                    14751 non-null  float64
 71  Penalties                 14751 non-null  float64
 72  Composure                 14751 non-null  float64
 73  Marking                   14751 non-null  float64
 74  StandingTackle            14751 non-null  float64
 75  SlidingTackle             14751 non-null  float64
 76  GKDiving                  14751 non-null  float64
 77  GKHandling                14751 non-null  float64
 78  GKKicking                 14751 non-null  float64
 79  GKPositioning             14751 non-null  float64
 80  GKReflexes                14751 non-null  float64
dtypes: float64(68), int64(4), object(9)
memory usage: 9.2+ MB


data.describe()


data.describe(include='O')


x=data['Nationality'].value_counts()
sns.barplot(y=x.index[0:10],x=x[0:10])
plt.ylabel("Nationality")
plt.xlabel("Frequency")

Text(0.5, 0, 'Frequency')


print("Total number of clubs are:",data['Club'].nunique())

Total number of clubs are: 651


#Top 20 clubs with highest number of players
x=data['Club'].value_counts()
sns.barplot(y=x.index[0:20],x=x[0:20])
plt.ylabel("Club")
plt.xlabel("Frequency")

Text(0.5, 0, 'Frequency')


#maximum and minimum potential and  overall performanced players 
top_potential=data.sort_values(by='Potential',ascending=False).head(10)
sns.barplot(x=top_potential['Potential'],y=top_potential['Name'])
plt.title("Top 10 Potential Players")
plt.xlabel("Potential")
plt.ylabel("Name")

Text(0, 0.5, 'Name')


#Top overall performance players
top_overall=data.sort_values(by='Overall',ascending=False).head(10)
sns.barplot(x=top_overall['Overall'],y=top_overall['Name'])
plt.title("Top 10 Overall Performance Players")
plt.xlabel("Overall")
plt.ylabel("Name")

Text(0, 0.5, 'Name')


#Top Valuable Players
top_value=data.sort_values(by='Value',ascending=False).head(10)
sns.barplot(x=top_value['Value'],y=top_overall['Name'])
plt.title("Top 10 Valuable Players")
plt.xlabel("Value")
plt.ylabel("Name")

Text(0, 0.5, 'Name')


top_value


sns.barplot(x=top_value['Value'],y=top_value['Name'])

<AxesSubplot:xlabel='Value', ylabel='Name'>


sns.countplot(data['Age'])

C:\Users\Rahul Gupta\anaconda3\envs\PyR\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

<AxesSubplot:xlabel='Age', ylabel='count'>


plt.figure(figsize=(8,8))
plt.scatter(x=data['Overall'],y=data['Potential'])
plt.xlabel("Overall rating")
plt.ylabel("Potential")
plt.title("Scatterplot of Potential v/s Overall Rating")

Text(0.5, 1.0, 'Scatterplot of Potential v/s Overall Rating')


#Top 20 teams with highest player's average Overall rating
club = data.groupby('Club')['Overall'].mean().reset_index().sort_values('Overall', ascending=True).tail(20)
sns.barplot(x=club['Overall'],y=club['Club'])

<AxesSubplot:xlabel='Overall', ylabel='Club'>


sns.countplot(data['Preferred Foot'])

C:\Users\Rahul Gupta\anaconda3\envs\PyR\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

<AxesSubplot:xlabel='Preferred Foot', ylabel='count'>


plt.figure(figsize=(8,8))
plt.scatter(x=data['Value'],y=data['Wage'])
plt.xlabel("Value")
plt.ylabel("Wage")
plt.title("Scatterplot of Value v/s Wage")

Text(0.5, 1.0, 'Scatterplot of Value v/s Wage')


plt.figure(figsize=(15,5))
sns.countplot(data['Position'])

C:\Users\Rahul Gupta\anaconda3\envs\PyR\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

<AxesSubplot:xlabel='Position', ylabel='count'>


sns.distplot(data['Value'])

C:\Users\Rahul Gupta\anaconda3\envs\PyR\lib\site-packages\seaborn\distributions.py:2557: FutureWarning:

`distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).

<AxesSubplot:xlabel='Value', ylabel='Density'>


sns.distplot(data['Wage'])

C:\Users\Rahul Gupta\anaconda3\envs\PyR\lib\site-packages\seaborn\distributions.py:2557: FutureWarning:

`distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).

<AxesSubplot:xlabel='Wage', ylabel='Density'>


player = data.groupby('Name')['Height'].mean().reset_index().sort_values('Height', ascending=True).tail(20)
sns.barplot(x=player['Height'],y=player['Name'])
plt.title("Top 20 tallest players")

Text(0.5, 1.0, 'Top 20 tallest players')


player = data.groupby('Name')['Weight'].mean().reset_index().sort_values('Weight', ascending=True).tail(20)
sns.barplot(x=player['Weight'],y=player['Name'])
plt.title("Top 20 heaviest players")

Text(0.5, 1.0, 'Top 20 heaviest players')


player = data.groupby('Name')['Crossing'].mean().reset_index().sort_values('Crossing', ascending=True).tail(20)
sns.barplot(x=player['Crossing'],y=player['Name'])
plt.title("Top 20 players who are good in crossing")

Text(0.5, 1.0, 'Top 20 players who are good in crossing')


player = data.groupby('Name')['Finishing'].mean().reset_index().sort_values('Finishing', ascending=True).tail(20)
sns.barplot(x=player['Finishing'],y=player['Name'])
plt.title("Top 20 players who are good in finishing the ball")

Text(0.5, 1.0, 'Top 20 players who are good in finishing the ball')


player = data.groupby('Name')['HeadingAccuracy'].mean().reset_index().sort_values('HeadingAccuracy', ascending=True).tail(20)
sns.barplot(x=player['HeadingAccuracy'],y=player['Name'])
plt.title("Top 20 players who are good at heading the ball")

Text(0.5, 1.0, 'Top 20 players who are good at heading the ball')


player= data.groupby('Name')['ShortPassing'].mean().reset_index().sort_values('ShortPassing', ascending=True).tail(20)
sns.barplot(x=player['ShortPassing'],y=player['Name'])
plt.title("Top 20 players who are good at short passing")

Text(0.5, 1.0, 'Top 20 players who are good at short passing')


player= data.groupby('Name')['Volleys'].mean().reset_index().sort_values('Volleys', ascending=True).tail(20)
sns.barplot(x=player['Volleys'],y=player['Name'])
plt.title("Top 20 players who are good at Volleys")

Text(0.5, 1.0, 'Top 20 players who are good at Volleys')


player= data.groupby('Name')['Dribbling'].mean().reset_index().sort_values('Dribbling', ascending=True).tail(20)
sns.barplot(x=player['Dribbling'],y=player['Name'])
plt.title("Top 20 players who are good at Dribbling")

Text(0.5, 1.0, 'Top 20 players who are good at Dribbling')


player= data.groupby('Name')['Curve'].mean().reset_index().sort_values('Curve', ascending=True).tail(20)
sns.barplot(x=player['Curve'],y=player['Name'])
plt.title("Top 20 players who are good at curving the ball")

Text(0.5, 1.0, 'Top 20 players who are good at curving the ball')


player= data.groupby('Name')['LongPassing'].mean().reset_index().sort_values('LongPassing', ascending=True).tail(20)
sns.barplot(x=player['LongPassing'],y=player['Name'])
plt.title("Top 20 players who are good at long pass")

Text(0.5, 1.0, 'Top 20 players who are good at long pass')


player= data.groupby('Name')['BallControl'].mean().reset_index().sort_values('BallControl', ascending=True).tail(20)
sns.barplot(x=player['BallControl'],y=player['Name'])
plt.title("Top 20 players who are good at ball control")

Text(0.5, 1.0, 'Top 20 players who are good at ball control')


player= data.groupby('Name')['Acceleration'].mean().reset_index().sort_values('Acceleration', ascending=True).tail(20)
sns.barplot(x=player['Acceleration'],y=player['Name'])
plt.title("Top 20 players who are good at accelerating the ball")

Text(0.5, 1.0, 'Top 20 players who are good at accelerating the ball')


player= data.groupby('Name')['SprintSpeed'].mean().reset_index().sort_values('SprintSpeed', ascending=True).tail(20)
sns.barplot(x=player['SprintSpeed'],y=player['Name'])
plt.title("Top 20 players who are good at sprinting")

Text(0.5, 1.0, 'Top 20 players who are good at sprinting')


player= data.groupby('Name')['Agility'].mean().reset_index().sort_values('Agility', ascending=True).tail(20)
sns.barplot(x=player['Agility'],y=player['Name'])
plt.title("Top 20 players agile players")

Text(0.5, 1.0, 'Top 20 players agile players')


player= data.groupby('Name')['Reactions'].mean().reset_index().sort_values('Reactions', ascending=True).tail(20)
sns.barplot(x=player['Reactions'],y=player['Name'])
plt.title("Top 20 players who is best in reaction")

Text(0.5, 1.0, 'Top 20 players who is best in reaction')


player= data.groupby('Name')['Reactions'].mean().reset_index().sort_values('Reactions', ascending=True).tail(20)
sns.barplot(x=player['Reactions'],y=player['Name'])
plt.title("Top 20 players who is best in reaction")

Text(0.5, 1.0, 'Top 20 players who is best in reaction')


player= data.groupby('Name')['Balance'].mean().reset_index().sort_values('Balance', ascending=True).tail(20)
sns.barplot(x=player['Balance'],y=player['Name'])
plt.title("Top 20 players with best balance")

Text(0.5, 1.0, 'Top 20 players with best balance')


player= data.groupby('Name')['ShotPower'].mean().reset_index().sort_values('ShotPower', ascending=True).tail(20)
sns.barplot(x=player['ShotPower'],y=player['Name'])
plt.title("Top 20 players with best shot power")

Text(0.5, 1.0, 'Top 20 players with best shot power')


player= data.groupby('Name')['Jumping'].mean().reset_index().sort_values('Jumping', ascending=True).tail(20)
sns.barplot(x=player['Jumping'],y=player['Name'])
plt.title("Top 20 players who are best jumpers")

Text(0.5, 1.0, 'Top 20 players who are best jumpers')


player= data.groupby('Name')['Stamina'].mean().reset_index().sort_values('Stamina', ascending=True).tail(20)
sns.barplot(x=player['Stamina'],y=player['Name'])
plt.title("Top 20 players having high stamina")

Text(0.5, 1.0, 'Top 20 players having high stamina')


player= data.groupby('Name')['Strength'].mean().reset_index().sort_values('Strength', ascending=True).tail(20)
sns.barplot(x=player['Strength'],y=player['Name'])
plt.title("Top 20 players with high strength")

Text(0.5, 1.0, 'Top 20 players with high strength')


player= data.groupby('Name')['LongShots'].mean().reset_index().sort_values('LongShots', ascending=True).tail(20)
sns.barplot(x=player['LongShots'],y=player['Name'])
plt.title("Top 20 players who are good at long shot")

Text(0.5, 1.0, 'Top 20 players who are good at long shot')


player= data.groupby('Name')['Aggression'].mean().reset_index().sort_values('Aggression', ascending=True).tail(20)
sns.barplot(x=player['Aggression'],y=player['Name'])
plt.title("Top 20 most aggressive players")

Text(0.5, 1.0, 'Top 20 most aggressive players')


player= data.groupby('Name')['Penalties'].mean().reset_index().sort_values('Penalties', ascending=True).tail(20)
sns.barplot(x=player['Penalties'],y=player['Name'])
plt.title("Top 20 players with penalties")

Text(0.5, 1.0, 'Top 20 players with penalties')


player= data.groupby('Name')['SlidingTackle'].mean().reset_index().sort_values('SlidingTackle', ascending=True).tail(20)
sns.barplot(x=player['SlidingTackle'],y=player['Name'])
plt.title("Top 20 players with best sliding tackle")

Text(0.5, 1.0, 'Top 20 players with best sliding tackle')


player= data.groupby('Name')['GKPositioning'].mean().reset_index().sort_values('GKPositioning', ascending=True).tail(20)
sns.barplot(x=player['GKPositioning'],y=player['Name'])
plt.title("Top 20 players with best GKPositioning")

Text(0.5, 1.0, 'Top 20 players with best GKPositioning')


plt.figure(figsize=(8,8))
plt.scatter(x=data['Age'],y=data['Overall'])
plt.xlabel("Age")
plt.ylabel("Overall")
plt.title("Scatterplot of Age v/s Overall")

Text(0.5, 1.0, 'Scatterplot of Age v/s Overall')


plt.figure(figsize=(8,8))
plt.scatter(x=data['Age'],y=data['Value'])
plt.xlabel("Age")
plt.ylabel("Value")
plt.title("Scatterplot of Age v/s value")

Text(0.5, 1.0, 'Scatterplot of Age v/s value')


plt.figure(figsize=(8,8))
plt.scatter(x=data['Age'],y=data['Crossing'])
plt.xlabel("Age")
plt.ylabel("Crossing")
plt.title("Scatterplot of Age v/s Crossing ")

Text(0.5, 1.0, 'Scatterplot of Age v/s Crossing ')


plt.figure(figsize=(8,8))
plt.scatter(x=data['Age'],y=data['Acceleration'])
plt.xlabel("Age")
plt.ylabel("Acceleration")
plt.title("Scatterplot of Age v/s Acceleration")

Text(0.5, 1.0, 'Scatterplot of Age v/s Acceleration')


plt.figure(figsize=(8,8))
plt.scatter(x=data['Age'],y=data['ShortPassing'])
plt.xlabel("Age")
plt.ylabel("ShortPassing")
plt.title("Scatterplot of Age v/s ShortPassing")

Text(0.5, 1.0, 'Scatterplot of Age v/s ShortPassing')


plt.figure(figsize=(8,8))
plt.scatter(x=data['Age'],y=data['Reactions'])
plt.xlabel("Age")
plt.ylabel("Reactions")
plt.title("Scatterplot of Age v/s Reactions")

Text(0.5, 1.0, 'Scatterplot of Age v/s Reactions')


plt.figure(figsize=(8,8))
plt.scatter(x=data['Dribbling'],y=data['BallControl'])
plt.xlabel("Dribbling")
plt.ylabel("BallControl")
plt.title("Scatterplot of Dribbling v/s BallControl")

Text(0.5, 1.0, 'Scatterplot of Dribbling v/s BallControl')


sns.lmplot(x = 'BallControl', y = 'Dribbling', data = data,col = 'Preferred Foot')

<seaborn.axisgrid.FacetGrid at 0x27bf82e4ac0>


fig = px.pie(data, names = "Work Rate",
             title = "<b>Counts in Work Rate</b>",
             hole = 0.4, template = "plotly_dark",
            width=600,
            height=500)
fig.show()


sns.boxplot(data['Age'])
plt.title("Boxplot of Age")

C:\Users\Rahul Gupta\anaconda3\envs\PyR\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

Text(0.5, 1.0, 'Boxplot of Age')


sns.boxplot(data['Overall'])
plt.title("Boxplot of Overall")

C:\Users\Rahul Gupta\anaconda3\envs\PyR\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

Text(0.5, 1.0, 'Boxplot of Overall')


sns.boxplot(data['Potential'])
plt.title("Boxplot of Potential")

C:\Users\Rahul Gupta\anaconda3\envs\PyR\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

Text(0.5, 1.0, 'Boxplot of Potential')


sns.boxplot(data['Value'])
plt.title("Boxplot of Value")

C:\Users\Rahul Gupta\anaconda3\envs\PyR\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

Text(0.5, 1.0, 'Boxplot of Value')


sns.boxplot(data['Wage'])
plt.title('Boxplot of Wage')

C:\Users\Rahul Gupta\anaconda3\envs\PyR\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

Text(0.5, 1.0, 'Boxplot of Wage')


sns.boxplot(data['Special'])
plt.title('Boxplot of Special')

C:\Users\Rahul Gupta\anaconda3\envs\PyR\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

Text(0.5, 1.0, 'Boxplot of Special')


sns.boxplot(data['International Reputation'])
plt.title('Boxplot of "International Reputation"')

C:\Users\Rahul Gupta\anaconda3\envs\PyR\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

Text(0.5, 1.0, 'Boxplot of "International Reputation"')


sns.boxplot(data['Weak Foot'])
plt.title("Boxplot of 'Weak Foot'")

C:\Users\Rahul Gupta\anaconda3\envs\PyR\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

Text(0.5, 1.0, "Boxplot of 'Weak Foot'")


sns.boxplot(data['Skill Moves'])
plt.title("Bixplot of 'Skill Moves'")

C:\Users\Rahul Gupta\anaconda3\envs\PyR\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

Text(0.5, 1.0, "Bixplot of 'Skill Moves'")


sns.boxplot(data['Height'])
plt.title("Boxplot of 'Height'")

C:\Users\Rahul Gupta\anaconda3\envs\PyR\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

Text(0.5, 1.0, "Boxplot of 'Height'")


sns.boxplot(data['Weight'])
plt.title("Boxplot of 'Weight'")

C:\Users\Rahul Gupta\anaconda3\envs\PyR\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

Text(0.5, 1.0, "Boxplot of 'Weight'")


numerical_col=data.select_dtypes(include=['int64','float64']).columns


#Lower and Upper fence of Outliers Identification
def lower_limit(x):
    return np.quantile(x,0.25)-1.5*(np.quantile(x,0.75)-np.quantile(x,0.25))

def upper_limit(x):
    return np.quantile(x,0.25)+1.5*(np.quantile(x,0.75)-np.quantile(x,0.25))


# Getting rid of non-integer features.
data2 = data.drop(columns=[ 'Name', 'Nationality', 'Club','Value','Wage','Preferred Foot','Work Rate','Body Type','Position', 'Joined','Contract Valid Until','Height','Weight','LS','ST','RS','LW','LF','CF','RF','RW','LAM','CAM','RAM','LM','LCM','CM','RCM','RM','LWB','LDM','CDM','RDM','RWB','LB','LCB','CB','RCB','RB'],axis=1)
X = data2.values
X = StandardScaler().fit_transform(X)
print(X)

[[ 1.27604112  4.00853692  3.71546904 ...  1.41220981  1.12857961
  -0.80764857]
 [ 1.7102333   4.00853692  3.71546904 ...  1.41220981  1.12857961
   0.1591048 ]
 [ 0.19056065  3.71825816  3.55156207 ...  1.41220981  1.45376768
   0.1591048 ]
 ...
 [-1.98040027 -2.81301389 -0.71001907 ... -0.17812724 -1.47292492
   0.80360705]
 [-1.76330418 -2.81301389 -0.87392604 ...  1.0941424  -0.82254879
  -0.48539744]
 [-1.98040027 -2.95815327 -0.87392604 ... -0.49619465  0.47820348
  -0.48539744]]


wcss=[]
score=[]
for i in (3,5,7):
    kmeans=KMeans(n_clusters=i,init='k-means++',random_state=0)
    kmeans.fit(X)
    cluster_labels = kmeans.fit_predict(X)
    score.append(metrics.silhouette_score(X, cluster_labels))
    wcss.append(kmeans.inertia_)


sns.set()
plt.plot([3,5,7],wcss)
plt.title("The elbow plot graph")
plt.xlabel("Number of Clusters")
plt.ylabel("WCSS")
plt.show()


sns.barplot(x=[3,5,7],y=score)
plt.title("Barplot Representing Silhouette Score of Different k Values")
plt.xlabel("k")
plt.ylabel("Silhouette Score")

Text(0, 0.5, 'Silhouette Score')


kmeans1=KMeans(n_clusters=7,init='k-means++',random_state=0)
Y=kmeans1.fit_predict(X)
print(Y)

[6 6 6 ... 0 0 3]


kmeans2=KMeans(n_clusters=3,init='k-means++',random_state=0)
Y=kmeans2.fit_predict(X)
print(Y)

[0 0 0 ... 1 1 2]


#Reducing the dimensionality of the Data
pca = PCA(n_components = 2)
X_principal = pca.fit_transform(X)
X_principal = pd.DataFrame(X_principal)
X_principal.columns = ['P1', 'P2']


import scipy.cluster.hierarchy as shc
plt.figure(figsize =(8, 8))
plt.title('Visualising the data')
Dendrogram = shc.dendrogram((shc.linkage(X_principal, method ='ward')))


#k=2
ac2 = AgglomerativeClustering(n_clusters = 2)
plt.figure(figsize =(6, 6))
plt.scatter(X_principal['P1'], X_principal['P2'], 
           c = ac2.fit_predict(X_principal), cmap ='rainbow')
plt.show()


#k=3
ac3 = AgglomerativeClustering(n_clusters = 3)
  
plt.figure(figsize =(6, 6))
plt.scatter(X_principal['P1'], X_principal['P2'],c = ac3.fit_predict(X_principal), cmap ='rainbow')
plt.show()


#k=4
ac4 = AgglomerativeClustering(n_clusters = 4)
  
plt.figure(figsize =(6, 6))
plt.scatter(X_principal['P1'], X_principal['P2'],
           c = ac4.fit_predict(X_principal), cmap ='rainbow')
plt.show()


#k=5
ac5 = AgglomerativeClustering(n_clusters = 5)
  
plt.figure(figsize =(6, 6))
plt.scatter(X_principal['P1'], X_principal['P2'],
            c = ac5.fit_predict(X_principal), cmap ='rainbow')
plt.show()


#k=6
ac6 = AgglomerativeClustering(n_clusters = 6)
  
plt.figure(figsize =(6, 6))
plt.scatter(X_principal['P1'], X_principal['P2'],
            c = ac6.fit_predict(X_principal), cmap ='rainbow')
plt.show()


k = [2, 3, 4, 5, 6]
from sklearn.metrics import silhouette_score  
# Appending the silhouette scores of the different models to the list
silhouette_scores = []
silhouette_scores.append(
        silhouette_score(X_principal, ac2.fit_predict(X_principal)))
silhouette_scores.append(
        silhouette_score(X_principal, ac3.fit_predict(X_principal)))
silhouette_scores.append(
        silhouette_score(X_principal, ac4.fit_predict(X_principal)))
silhouette_scores.append(
        silhouette_score(X_principal, ac5.fit_predict(X_principal)))
silhouette_scores.append(
        silhouette_score(X_principal, ac6.fit_predict(X_principal)))
  
# Plotting a bar graph to compare the results
plt.bar(k, silhouette_scores)
plt.xlabel('Number of clusters', fontsize = 20)
plt.ylabel('S(i)', fontsize = 20)
plt.show()


from sklearn.cluster import DBSCAN


# Compute DBSCAN
db = DBSCAN(eps=0.3, min_samples=10).fit(X_principal)
core_samples_mask = np.zeros_like(db.labels_, dtype=bool)
core_samples_mask[db.core_sample_indices_] = True
labels = db.labels_

# Number of clusters in labels, ignoring noise if present.
n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)

print('Estimated number of clusters: %d' % n_clusters_)
print("Silhouette Coefficient: %0.3f"
      % metrics.silhouette_score(X, labels))

Estimated number of clusters: 8
Silhouette Coefficient: -0.099

	ID	Name	Age	Photo	Nationality	Flag	Overall	Potential	Club	Club Logo	Value	Wage	Special	Preferred Foot	International Reputation	Weak Foot	Skill Moves	Work Rate	Body Type	Real Face	Position	Jersey Number	Joined	Loaned From	Contract Valid Until	Height	Weight	LS	ST	RS	LW	LF	CF	RF	RW	LAM	CAM	RAM	LM	LCM	CM	RCM	RM	LWB	LDM	CDM	RDM	RWB	LB	LCB	CB	RCB	RB	Crossing	Finishing	HeadingAccuracy	ShortPassing	Volleys	Dribbling	Curve	FKAccuracy	LongPassing	BallControl	Acceleration	SprintSpeed	Agility	Reactions	Balance	ShotPower	Jumping	Stamina	Strength	LongShots	Aggression	Interceptions	Positioning	Vision	Penalties	Composure	Marking	StandingTackle	SlidingTackle	GKDiving	GKHandling	GKKicking	GKPositioning	GKReflexes	Release Clause
0	158023	L. Messi	31	https://cdn.sofifa.org/players/4/19/158023.png	Argentina	https://cdn.sofifa.org/flags/52.png	94	94	FC Barcelona	https://cdn.sofifa.org/teams/2/light/241.png	€110.5M	€565K	2202	Left	5.0	4.0	4.0	Medium/ Medium	Messi	Yes	RF	10.0	Jul 1, 2004	NaN	2021	5'7	159lbs	88+2	88+2	88+2	92+2	93+2	93+2	93+2	92+2	93+2	93+2	93+2	91+2	84+2	84+2	84+2	91+2	64+2	61+2	61+2	61+2	64+2	59+2	47+2	47+2	47+2	59+2	84.0	95.0	70.0	90.0	86.0	97.0	93.0	94.0	87.0	96.0	91.0	86.0	91.0	95.0	95.0	85.0	68.0	72.0	59.0	94.0	48.0	22.0	94.0	94.0	75.0	96.0	33.0	28.0	26.0	6.0	11.0	15.0	14.0	8.0	€226.5M
1	20801	Cristiano Ronaldo	33	https://cdn.sofifa.org/players/4/19/20801.png	Portugal	https://cdn.sofifa.org/flags/38.png	94	94	Juventus	https://cdn.sofifa.org/teams/2/light/45.png	€77M	€405K	2228	Right	5.0	4.0	5.0	High/ Low	C. Ronaldo	Yes	ST	7.0	Jul 10, 2018	NaN	2022	6'2	183lbs	91+3	91+3	91+3	89+3	90+3	90+3	90+3	89+3	88+3	88+3	88+3	88+3	81+3	81+3	81+3	88+3	65+3	61+3	61+3	61+3	65+3	61+3	53+3	53+3	53+3	61+3	84.0	94.0	89.0	81.0	87.0	88.0	81.0	76.0	77.0	94.0	89.0	91.0	87.0	96.0	70.0	95.0	95.0	88.0	79.0	93.0	63.0	29.0	95.0	82.0	85.0	95.0	28.0	31.0	23.0	7.0	11.0	15.0	14.0	11.0	€127.1M
2	190871	Neymar Jr	26	https://cdn.sofifa.org/players/4/19/190871.png	Brazil	https://cdn.sofifa.org/flags/54.png	92	93	Paris Saint-Germain	https://cdn.sofifa.org/teams/2/light/73.png	€118.5M	€290K	2143	Right	5.0	5.0	5.0	High/ Medium	Neymar	Yes	LW	10.0	Aug 3, 2017	NaN	2022	5'9	150lbs	84+3	84+3	84+3	89+3	89+3	89+3	89+3	89+3	89+3	89+3	89+3	88+3	81+3	81+3	81+3	88+3	65+3	60+3	60+3	60+3	65+3	60+3	47+3	47+3	47+3	60+3	79.0	87.0	62.0	84.0	84.0	96.0	88.0	87.0	78.0	95.0	94.0	90.0	96.0	94.0	84.0	80.0	61.0	81.0	49.0	82.0	56.0	36.0	89.0	87.0	81.0	94.0	27.0	24.0	33.0	9.0	9.0	15.0	15.0	11.0	€228.1M
3	193080	De Gea	27	https://cdn.sofifa.org/players/4/19/193080.png	Spain	https://cdn.sofifa.org/flags/45.png	91	93	Manchester United	https://cdn.sofifa.org/teams/2/light/11.png	€72M	€260K	1471	Right	4.0	3.0	1.0	Medium/ Medium	Lean	Yes	GK	1.0	Jul 1, 2011	NaN	2020	6'4	168lbs	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	17.0	13.0	21.0	50.0	13.0	18.0	21.0	19.0	51.0	42.0	57.0	58.0	60.0	90.0	43.0	31.0	67.0	43.0	64.0	12.0	38.0	30.0	12.0	68.0	40.0	68.0	15.0	21.0	13.0	90.0	85.0	87.0	88.0	94.0	€138.6M
4	192985	K. De Bruyne	27	https://cdn.sofifa.org/players/4/19/192985.png	Belgium	https://cdn.sofifa.org/flags/7.png	91	92	Manchester City	https://cdn.sofifa.org/teams/2/light/10.png	€102M	€355K	2281	Right	4.0	5.0	4.0	High/ High	Normal	Yes	RCM	7.0	Aug 30, 2015	NaN	2023	5'11	154lbs	82+3	82+3	82+3	87+3	87+3	87+3	87+3	87+3	88+3	88+3	88+3	88+3	87+3	87+3	87+3	88+3	77+3	77+3	77+3	77+3	77+3	73+3	66+3	66+3	66+3	73+3	93.0	82.0	55.0	92.0	82.0	86.0	85.0	83.0	91.0	91.0	78.0	76.0	79.0	91.0	77.0	91.0	63.0	90.0	75.0	91.0	76.0	61.0	87.0	94.0	79.0	88.0	68.0	58.0	51.0	15.0	13.0	5.0	10.0	13.0	€196.4M

	Name	Age	Nationality	Overall	Potential	Club	Value	Wage	Special	Preferred Foot	International Reputation	Weak Foot	Skill Moves	Work Rate	Body Type	Position	Jersey Number	Joined	Contract Valid Until	Height	Weight	LS	ST	RS	LW	LF	CF	RF	RW	LAM	CAM	RAM	LM	LCM	CM	RCM	RM	LWB	LDM	CDM	RDM	RWB	LB	LCB	CB	RCB	RB	Crossing	Finishing	HeadingAccuracy	ShortPassing	Volleys	Dribbling	Curve	FKAccuracy	LongPassing	BallControl	Acceleration	SprintSpeed	Agility	Reactions	Balance	ShotPower	Jumping	Stamina	Strength	LongShots	Aggression	Interceptions	Positioning	Vision	Penalties	Composure	Marking	StandingTackle	SlidingTackle	GKDiving	GKHandling	GKKicking	GKPositioning	GKReflexes
0	L. Messi	31	Argentina	94	94	FC Barcelona	110500000.0	565000.0	2202	Left	5.0	4.0	4.0	Medium/ Medium	Messi	RF	10.0	2004	2021	5.583333	159.0	90.0	90.0	90.0	94.0	95.0	95.0	95.0	94.0	95.0	95.0	95.0	93.0	86.0	86.0	86.0	93.0	66.0	63.0	63.0	63.0	66.0	61.0	49.0	49.0	49.0	61.0	84.0	95.0	70.0	90.0	86.0	97.0	93.0	94.0	87.0	96.0	91.0	86.0	91.0	95.0	95.0	85.0	68.0	72.0	59.0	94.0	48.0	22.0	94.0	94.0	75.0	96.0	33.0	28.0	26.0	6.0	11.0	15.0	14.0	8.0
1	Cristiano Ronaldo	33	Portugal	94	94	Juventus	77000000.0	405000.0	2228	Right	5.0	4.0	5.0	High/ Low	C. Ronaldo	ST	7.0	2018	2022	6.166667	183.0	94.0	94.0	94.0	92.0	93.0	93.0	93.0	92.0	91.0	91.0	91.0	91.0	84.0	84.0	84.0	91.0	68.0	64.0	64.0	64.0	68.0	64.0	56.0	56.0	56.0	64.0	84.0	94.0	89.0	81.0	87.0	88.0	81.0	76.0	77.0	94.0	89.0	91.0	87.0	96.0	70.0	95.0	95.0	88.0	79.0	93.0	63.0	29.0	95.0	82.0	85.0	95.0	28.0	31.0	23.0	7.0	11.0	15.0	14.0	11.0
2	Neymar Jr	26	Brazil	92	93	Paris Saint-Germain	118500000.0	290000.0	2143	Right	5.0	5.0	5.0	High/ Medium	Neymar	LW	10.0	2017	2022	5.750000	150.0	87.0	87.0	87.0	92.0	92.0	92.0	92.0	92.0	92.0	92.0	92.0	91.0	84.0	84.0	84.0	91.0	68.0	63.0	63.0	63.0	68.0	63.0	50.0	50.0	50.0	63.0	79.0	87.0	62.0	84.0	84.0	96.0	88.0	87.0	78.0	95.0	94.0	90.0	96.0	94.0	84.0	80.0	61.0	81.0	49.0	82.0	56.0	36.0	89.0	87.0	81.0	94.0	27.0	24.0	33.0	9.0	9.0	15.0	15.0	11.0
4	K. De Bruyne	27	Belgium	91	92	Manchester City	102000000.0	355000.0	2281	Right	4.0	5.0	4.0	High/ High	Normal	RCM	7.0	2015	2023	5.916667	154.0	85.0	85.0	85.0	90.0	90.0	90.0	90.0	90.0	91.0	91.0	91.0	91.0	90.0	90.0	90.0	91.0	80.0	80.0	80.0	80.0	80.0	76.0	69.0	69.0	69.0	76.0	93.0	82.0	55.0	92.0	82.0	86.0	85.0	83.0	91.0	91.0	78.0	76.0	79.0	91.0	77.0	91.0	63.0	90.0	75.0	91.0	76.0	61.0	87.0	94.0	79.0	88.0	68.0	58.0	51.0	15.0	13.0	5.0	10.0	13.0
5	E. Hazard	27	Belgium	91	91	Chelsea	93000000.0	340000.0	2142	Right	4.0	4.0	4.0	High/ Medium	Normal	LF	10.0	2012	2020	5.666667	163.0	86.0	86.0	86.0	92.0	91.0	91.0	91.0	92.0	92.0	92.0	92.0	92.0	85.0	85.0	85.0	92.0	69.0	66.0	66.0	66.0	69.0	63.0	52.0	52.0	52.0	63.0	81.0	84.0	61.0	89.0	80.0	95.0	83.0	79.0	83.0	94.0	94.0	88.0	95.0	90.0	94.0	82.0	56.0	83.0	66.0	80.0	54.0	41.0	87.0	89.0	86.0	91.0	34.0	27.0	22.0	11.0	12.0	6.0	8.0	8.0

	Age	Overall	Potential	Value	Wage	Special	International Reputation	Weak Foot	Skill Moves	Jersey Number	Height	Weight	LS	ST	RS	LW	LF	CF	RF	RW	LAM	CAM	RAM	LM	LCM	CM	RCM	RM	LWB	LDM	CDM	RDM	RWB	LB	LCB	CB	RCB	RB	Crossing	Finishing	HeadingAccuracy	ShortPassing	Volleys	Dribbling	Curve	FKAccuracy	LongPassing	BallControl	Acceleration	SprintSpeed	Agility	Reactions	Balance	ShotPower	Jumping	Stamina	Strength	LongShots	Aggression	Interceptions	Positioning	Vision	Penalties	Composure	Marking	StandingTackle	SlidingTackle	GKDiving	GKHandling	GKKicking	GKPositioning	GKReflexes
count	14751.000000	14751.000000	14751.000000	1.475100e+04	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000	14751.000000
mean	25.122229	66.381466	71.331842	2.550233e+06	9987.526269	1666.424039	1.117348	3.001220	2.523422	19.519083	5.917345	164.105688	59.708969	59.708969	59.708969	60.937292	60.612501	60.612501	60.612501	60.937292	60.891668	60.891668	60.891668	61.656905	60.190835	60.190835	60.190835	61.656905	59.569453	58.907261	58.907261	58.907261	59.569453	58.883059	57.733849	57.733849	57.733849	58.883059	54.151922	49.552505	56.990238	62.581452	46.590536	60.420785	51.172937	46.409667	56.101213	63.061555	67.816826	67.878720	66.355637	62.165074	66.598332	59.475425	66.079384	67.372178	65.925632	51.255101	59.734662	50.638804	54.667887	55.398278	52.000678	60.308793	51.470748	52.119314	49.840689	10.504305	10.558199	10.560030	10.529456	10.506271
std	4.606411	6.890162	6.101229	5.832472e+06	22828.925608	198.213504	0.401174	0.635342	0.616368	15.699233	0.210182	14.777161	9.168249	9.168249	9.168249	9.925666	9.886656	9.886656	9.886656	9.925666	9.822199	9.822199	9.822199	9.312767	8.885386	8.885386	8.885386	9.312767	9.025698	10.126900	10.126900	10.126900	9.025698	9.565656	11.723744	11.723744	11.723744	9.565656	14.164751	16.344256	11.619529	9.845759	14.793798	12.551619	15.174564	15.107819	12.401771	10.047319	11.805581	11.537182	12.363567	8.867526	12.161967	13.262320	11.552322	11.283637	12.573126	15.766377	14.413970	18.750290	14.703792	12.937831	12.532761	10.233095	17.166916	19.082899	19.078293	3.099300	3.080962	3.144094	3.075248	3.103275
min	16.000000	46.000000	48.000000	0.000000e+00	1000.000000	1000.000000	1.000000	1.000000	2.000000	2.000000	5.083333	110.000000	33.000000	33.000000	33.000000	27.000000	29.000000	29.000000	29.000000	27.000000	29.000000	29.000000	29.000000	29.000000	32.000000	32.000000	32.000000	29.000000	32.000000	30.000000	30.000000	30.000000	32.000000	31.000000	27.000000	27.000000	27.000000	31.000000	11.000000	10.000000	15.000000	20.000000	10.000000	14.000000	11.000000	10.000000	19.000000	25.000000	20.000000	25.000000	23.000000	21.000000	22.000000	14.000000	28.000000	27.000000	25.000000	11.000000	13.000000	10.000000	11.000000	12.000000	12.000000	29.000000	10.000000	10.000000	10.000000	1.000000	1.000000	1.000000	1.000000	1.000000
25%	21.000000	62.000000	67.000000	3.500000e+05	1000.000000	1524.000000	1.000000	3.000000	2.000000	8.000000	5.750000	154.000000	53.000000	53.000000	53.000000	55.000000	54.000000	54.000000	54.000000	55.000000	55.000000	55.000000	55.000000	56.000000	54.000000	54.000000	54.000000	56.000000	53.000000	52.000000	52.000000	52.000000	53.000000	52.000000	48.000000	48.000000	48.000000	52.000000	44.000000	36.000000	49.000000	57.000000	35.000000	54.000000	39.000000	34.000000	49.000000	58.000000	62.000000	62.000000	59.000000	56.000000	60.000000	51.000000	59.000000	61.000000	59.000000	40.000000	50.000000	35.000000	46.000000	47.000000	42.000000	53.000000	38.000000	36.000000	33.000000	8.000000	8.000000	8.000000	8.000000	8.000000
50%	25.000000	66.000000	71.000000	7.250000e+05	3000.000000	1669.000000	1.000000	3.000000	2.000000	17.000000	5.916667	163.000000	60.000000	60.000000	60.000000	62.000000	62.000000	62.000000	62.000000	62.000000	62.000000	62.000000	62.000000	63.000000	60.000000	60.000000	60.000000	63.000000	60.000000	60.000000	60.000000	60.000000	60.000000	60.000000	60.000000	60.000000	60.000000	60.000000	56.000000	52.000000	58.000000	64.000000	46.000000	62.000000	51.000000	44.000000	58.000000	64.000000	69.000000	69.000000	68.000000	62.000000	68.000000	61.000000	67.000000	68.000000	67.000000	54.000000	61.000000	56.000000	57.000000	57.000000	52.000000	61.000000	56.000000	59.000000	56.000000	10.000000	11.000000	11.000000	10.000000	10.000000
75%	28.000000	71.000000	75.000000	2.200000e+06	9000.000000	1806.000000	1.000000	3.000000	3.000000	26.000000	6.083333	174.000000	66.000000	66.000000	66.000000	68.000000	67.000000	67.000000	67.000000	68.000000	68.000000	68.000000	68.000000	68.000000	66.000000	66.000000	66.000000	68.000000	66.000000	66.000000	66.000000	66.000000	66.000000	66.000000	67.000000	67.000000	67.000000	66.000000	65.000000	63.000000	65.000000	69.000000	58.000000	69.000000	63.000000	58.000000	65.000000	70.000000	76.000000	76.000000	75.000000	68.000000	75.000000	69.000000	74.000000	75.000000	75.000000	64.000000	70.000000	65.000000	65.000000	65.000000	61.000000	68.000000	65.000000	67.000000	65.000000	13.000000	13.000000	13.000000	13.000000	13.000000
max	41.000000	94.000000	95.000000	1.185000e+08	565000.000000	2346.000000	5.000000	5.000000	5.000000	99.000000	6.666667	243.000000	94.000000	94.000000	94.000000	94.000000	95.000000	95.000000	95.000000	94.000000	95.000000	95.000000	95.000000	93.000000	91.000000	91.000000	91.000000	93.000000	88.000000	90.000000	90.000000	90.000000	88.000000	87.000000	90.000000	90.000000	90.000000	87.000000	93.000000	95.000000	94.000000	93.000000	90.000000	97.000000	94.000000	94.000000	93.000000	96.000000	97.000000	96.000000	96.000000	96.000000	96.000000	95.000000	95.000000	96.000000	97.000000	94.000000	95.000000	92.000000	95.000000	94.000000	92.000000	96.000000	94.000000	93.000000	91.000000	37.000000	33.000000	41.000000	33.000000	37.000000

	Name	Age	Nationality	Overall	Potential	Club	Value	Wage	Special	Preferred Foot	International Reputation	Weak Foot	Skill Moves	Work Rate	Body Type	Position	Jersey Number	Joined	Contract Valid Until	Height	Weight	LS	ST	RS	LW	LF	CF	RF	RW	LAM	CAM	RAM	LM	LCM	CM	RCM	RM	LWB	LDM	CDM	RDM	RWB	LB	LCB	CB	RCB	RB	Crossing	Finishing	HeadingAccuracy	ShortPassing	Volleys	Dribbling	Curve	FKAccuracy	LongPassing	BallControl	Acceleration	SprintSpeed	Agility	Reactions	Balance	ShotPower	Jumping	Stamina	Strength	LongShots	Aggression	Interceptions	Positioning	Vision	Penalties	Composure	Marking	StandingTackle	SlidingTackle	GKDiving	GKHandling	GKKicking	GKPositioning	GKReflexes
2	Neymar Jr	26	Brazil	92	93	Paris Saint-Germain	118500000.0	290000.0	2143	Right	5.0	5.0	5.0	High/ Medium	Neymar	LW	10.0	2017	2022	5.750000	150.0	87.0	87.0	87.0	92.0	92.0	92.0	92.0	92.0	92.0	92.0	92.0	91.0	84.0	84.0	84.0	91.0	68.0	63.0	63.0	63.0	68.0	63.0	50.0	50.0	50.0	63.0	79.0	87.0	62.0	84.0	84.0	96.0	88.0	87.0	78.0	95.0	94.0	90.0	96.0	94.0	84.0	80.0	61.0	81.0	49.0	82.0	56.0	36.0	89.0	87.0	81.0	94.0	27.0	24.0	33.0	9.0	9.0	15.0	15.0	11.0
0	L. Messi	31	Argentina	94	94	FC Barcelona	110500000.0	565000.0	2202	Left	5.0	4.0	4.0	Medium/ Medium	Messi	RF	10.0	2004	2021	5.583333	159.0	90.0	90.0	90.0	94.0	95.0	95.0	95.0	94.0	95.0	95.0	95.0	93.0	86.0	86.0	86.0	93.0	66.0	63.0	63.0	63.0	66.0	61.0	49.0	49.0	49.0	61.0	84.0	95.0	70.0	90.0	86.0	97.0	93.0	94.0	87.0	96.0	91.0	86.0	91.0	95.0	95.0	85.0	68.0	72.0	59.0	94.0	48.0	22.0	94.0	94.0	75.0	96.0	33.0	28.0	26.0	6.0	11.0	15.0	14.0	8.0
4	K. De Bruyne	27	Belgium	91	92	Manchester City	102000000.0	355000.0	2281	Right	4.0	5.0	4.0	High/ High	Normal	RCM	7.0	2015	2023	5.916667	154.0	85.0	85.0	85.0	90.0	90.0	90.0	90.0	90.0	91.0	91.0	91.0	91.0	90.0	90.0	90.0	91.0	80.0	80.0	80.0	80.0	80.0	76.0	69.0	69.0	69.0	76.0	93.0	82.0	55.0	92.0	82.0	86.0	85.0	83.0	91.0	91.0	78.0	76.0	79.0	91.0	77.0	91.0	63.0	90.0	75.0	91.0	76.0	61.0	87.0	94.0	79.0	88.0	68.0	58.0	51.0	15.0	13.0	5.0	10.0	13.0
5	E. Hazard	27	Belgium	91	91	Chelsea	93000000.0	340000.0	2142	Right	4.0	4.0	4.0	High/ Medium	Normal	LF	10.0	2012	2020	5.666667	163.0	86.0	86.0	86.0	92.0	91.0	91.0	91.0	92.0	92.0	92.0	92.0	92.0	85.0	85.0	85.0	92.0	69.0	66.0	66.0	66.0	69.0	63.0	52.0	52.0	52.0	63.0	81.0	84.0	61.0	89.0	80.0	95.0	83.0	79.0	83.0	94.0	94.0	88.0	95.0	90.0	94.0	82.0	56.0	83.0	66.0	80.0	54.0	41.0	87.0	89.0	86.0	91.0	34.0	27.0	22.0	11.0	12.0	6.0	8.0	8.0
15	P. Dybala	24	Argentina	89	94	Juventus	89000000.0	205000.0	2092	Left	3.0	3.0	4.0	High/ Medium	Normal	LF	21.0	2015	2022	5.833333	165.0	86.0	86.0	86.0	90.0	89.0	89.0	89.0	90.0	90.0	90.0	90.0	89.0	82.0	82.0	82.0	89.0	65.0	61.0	61.0	61.0	65.0	59.0	48.0	48.0	48.0	59.0	82.0	84.0	68.0	87.0	88.0	92.0	88.0	88.0	75.0	92.0	87.0	83.0	91.0	86.0	85.0	82.0	75.0	80.0	65.0	88.0	48.0	32.0	84.0	87.0	86.0	84.0	23.0	20.0	20.0	5.0	4.0	4.0	5.0	8.0
16	H. Kane	24	England	89	91	Tottenham Hotspur	83500000.0	205000.0	2165	Right	3.0	4.0	3.0	High/ High	Normal	ST	9.0	2010	2024	6.166667	196.0	89.0	89.0	89.0	85.0	87.0	87.0	87.0	85.0	85.0	85.0	85.0	84.0	82.0	82.0	82.0	84.0	68.0	69.0	69.0	69.0	68.0	65.0	63.0	63.0	63.0	65.0	75.0	94.0	85.0	80.0	84.0	80.0	78.0	68.0	82.0	84.0	68.0	72.0	71.0	91.0	71.0	88.0	78.0	89.0	84.0	85.0	76.0	35.0	93.0	80.0	90.0	89.0	56.0	36.0	38.0	8.0	10.0	11.0	14.0	11.0
25	K. Mbappé	19	France	88	95	Paris Saint-Germain	81000000.0	100000.0	2118	Right	3.0	4.0	5.0	High/ Medium	Lean	RM	10.0	2018	2022	5.833333	161.0	88.0	88.0	88.0	90.0	90.0	90.0	90.0	90.0	89.0	89.0	89.0	89.0	81.0	81.0	81.0	89.0	69.0	65.0	65.0	65.0	69.0	65.0	57.0	57.0	57.0	65.0	77.0	88.0	77.0	82.0	78.0	90.0	77.0	63.0	73.0	91.0	96.0	96.0	92.0	87.0	83.0	79.0	75.0	83.0	71.0	78.0	62.0	38.0	88.0	82.0	70.0	86.0	34.0	34.0	32.0	13.0	5.0	7.0	11.0	6.0
7	L. Suárez	31	Uruguay	91	91	FC Barcelona	80000000.0	455000.0	2346	Right	5.0	4.0	3.0	High/ Medium	Normal	RS	9.0	2014	2021	6.000000	190.0	92.0	92.0	92.0	91.0	92.0	92.0	92.0	91.0	90.0	90.0	90.0	89.0	84.0	84.0	84.0	89.0	74.0	73.0	73.0	73.0	74.0	71.0	68.0	68.0	68.0	71.0	77.0	93.0	77.0	82.0	88.0	87.0	86.0	84.0	64.0	90.0	86.0	75.0	82.0	92.0	83.0	86.0	69.0	90.0	83.0	85.0	87.0	41.0	92.0	84.0	85.0	85.0	62.0	45.0	38.0	27.0	25.0	31.0	33.0	37.0
17	A. Griezmann	27	France	89	90	Atlético Madrid	78000000.0	145000.0	2246	Left	4.0	3.0	4.0	High/ High	Lean	CAM	7.0	2014	2023	5.750000	161.0	89.0	89.0	89.0	90.0	90.0	90.0	90.0	90.0	89.0	89.0	89.0	89.0	83.0	83.0	83.0	89.0	73.0	70.0	70.0	70.0	73.0	70.0	64.0	64.0	64.0	70.0	82.0	90.0	84.0	83.0	87.0	88.0	84.0	78.0	76.0	90.0	88.0	85.0	90.0	90.0	80.0	80.0	90.0	83.0	62.0	82.0	69.0	35.0	91.0	83.0	79.0	87.0	59.0	47.0	48.0	14.0	8.0	14.0	13.0	14.0
1	Cristiano Ronaldo	33	Portugal	94	94	Juventus	77000000.0	405000.0	2228	Right	5.0	4.0	5.0	High/ Low	C. Ronaldo	ST	7.0	2018	2022	6.166667	183.0	94.0	94.0	94.0	92.0	93.0	93.0	93.0	92.0	91.0	91.0	91.0	91.0	84.0	84.0	84.0	91.0	68.0	64.0	64.0	64.0	68.0	64.0	56.0	56.0	56.0	64.0	84.0	94.0	89.0	81.0	87.0	88.0	81.0	76.0	77.0	94.0	89.0	91.0	87.0	96.0	70.0	95.0	95.0	88.0	79.0	93.0	63.0	29.0	95.0	82.0	85.0	95.0	28.0	31.0	23.0	7.0	11.0	15.0	14.0	11.0

Data Cleaning¶

Exploratory Data Analysis¶

Outlier Detection¶

K-Means Clustering¶

Agglomerative clustering¶

DBScan¶

	Name	Nationality	Club	Preferred Foot	Work Rate	Body Type	Position	Joined	Contract Valid Until
count	14751	14751	14751	14751	14751	14751	14751	14751	14751
unique	14047	160	651	2	9	9	26	20	9
top	J. Rodríguez	England	Arsenal	Right	Medium/ Medium	Normal	ST	2018	2019
freq	8	1320	30	11121	7122	8379	1924	5934	4201